Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to optimal choices and best practices in decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    choice or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.54
     awakeFromNib
    -0.50
    Kjelder
    -0.46
     capability
    -0.44
     MessageBoxIcon
    -0.43
     []).
    -0.43
     חיצוניים
    -0.42
     Cadena
    -0.42
     Cassidy
    -0.41
     Capabilities
    -0.41
    POSITIVE LOGITS
    Optimal
    0.81
     optimal
    0.73
    optimal
    0.73
     Optimal
    0.72
    Optim
    0.70
     optimise
    0.66
    optimize
    0.66
     Optimum
    0.66
     optimisation
    0.66
     optimize
    0.65
    Act Density 0.021%

    No Known Activations